Disease prediction method and system for intelligent scale

Abstract

The invention relates to the technical field of medical health monitoring, in particular to a disease prediction method and system for an intelligent scale, and the method comprises the steps: obtaining a first data set which comprises a plurality of first data sets, and each first data set comprises a reference face image, a reference fingerprint image and a reference body weight time sequence; the detection information comprises a target face image, a target fingerprint image, a target body weight group and a target face temperature point set, determining a target data group based on the target fingerprint image and the target face image corresponding to the detection information, obtaining a target body weight time sequence based on the target body weight group, and sending the target body weight time sequence to the intelligent scale, and the prediction feedback unit is used for obtaining a historical information set, determining a predicted disease sequence according to the target body weight time sequence and the historical information set, and sending the predicted disease sequence to an initiating end of a prediction instruction based on the prediction feedback unit to realize disease prediction. According to the invention, disease prediction can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical health monitoring, and in particular to a disease prediction method and system for a smart scale. Background Art

[0002] In the rapidly developing digital age, health monitoring technology is undergoing a profound transformation from the traditional medical model to intelligent and personalized directions. Although traditional health monitoring methods, such as annual physical examinations, can provide a certain degree of health assessment, their frequency is low, feedback is delayed, and they often focus on the symptoms of existing diseases, making it difficult to achieve early warning of health risks. Therefore, how to predict diseases has become an urgent problem to be solved.

[0003] Existing health monitoring methods often require users to go to the hospital for physical examinations regularly, and use the results of the physical examinations to determine whether they have a disease or to predict the disease.

[0004] Although the above methods can predict diseases, it is difficult to monitor the health changes of users in a timely manner. In addition, during physical examinations, physical examinations are mostly based on prior knowledge or known diseases, which makes it difficult to conduct targeted examinations. Therefore, how to predict diseases has become an urgent problem to be solved. Summary of the invention

[0005] The present invention provides a disease prediction method for a smart scale and a computer-readable storage medium, the main purpose of which is to achieve disease prediction.

[0006] To achieve the above object, the present invention provides a disease prediction method for a smart scale, comprising:

[0007] receiving a prediction instruction, and confirming a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit, and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit, and a facial temperature detection unit;

[0008] Confirming receipt of a data collection instruction from a data collection unit, and acquiring a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time;

[0009] Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups;

[0010] Using the target facial image corresponding to the detection information, a target data group is identified in the second data group sequence, and using the target weight group corresponding to the detection information to update the reference weight time series corresponding to the target data group to obtain the target weight time series;

[0011] Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time;

[0012] Acquire one or more target information sets based on the historical information sets;

[0013] The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

[0014] Optionally, the step of obtaining the detection information by using the started smart scale includes:

[0015] The target weight is obtained based on the weight collection unit, and the time of obtaining the target weight is recorded to obtain the weight collection time, and the target fingerprint image and the target facial image are obtained by using the fingerprint collection unit and the facial collection unit respectively;

[0016] Acquire a target facial temperature point set using a facial temperature detection unit and a pre-constructed facial acupoint set, wherein the facial acupoint set includes a plurality of facial acupoints, and the facial acupoints correspond one-to-one to the target facial temperature;

[0017] The target weight, weight collection time, target fingerprint image, target facial image and target facial temperature point set are summarized to obtain the detection information.

[0018] Optionally, the step of identifying a second data set sequence in the first data set based on the target fingerprint image corresponding to the detection information includes:

[0019] Extracting first data groups from the first data group set in sequence, and performing the following operations on the extracted first data groups:

[0020] Acquire fingerprint similarities between a reference fingerprint image and a target fingerprint image in the first data group, and summarize the fingerprint similarities to obtain a fingerprint similarity set;

[0021] Sorting the fingerprint similarities in the fingerprint similarity set in descending order of fingerprint similarity to obtain an initial fingerprint similarity sequence;

[0022] A target fingerprint similarity sequence is obtained using a preset first screening value and an initial fingerprint similarity sequence, wherein the fingerprint similarities in the target fingerprint similarity sequence are all greater than or equal to the first screening value, and a second data group sequence is confirmed based on the target fingerprint similarity sequence, wherein the second data groups in the second data group sequence correspond one-to-one to the target fingerprint similarities in the target fingerprint similarity sequence.

[0023] Optionally, acquiring one or more target information sets based on the historical information set includes:

[0024] According to the disease names corresponding to the historical information in the historical information set, the historical information is aggregated to obtain one or more initial information sets;

[0025] For each of the one or more initial information sets, the following operations are performed:

[0026] The following operations are performed for each historical information in the initial information set:

[0027] The last patient weight group is identified in the patient weight time series corresponding to the historical information to obtain the diseased weight group, and a screening time series segment is identified in the patient weight time series corresponding to the historical information based on a preset sliding window and taking the diseased weight group as a starting point, wherein the screening time series segment includes multiple screening weight groups, and the screening weight variance is obtained based on the multiple screening weight groups corresponding to the screening time series segment, wherein the screening weight variance is the variance of the patient weight corresponding to the multiple screening weight groups;

[0028] Compare the screening weight variance with a preset screening variance threshold; if the screening weight variance is greater than or equal to the screening variance threshold, update the sliding window using a preset sliding step to obtain a first update window; take the first update window as the sliding window, return to the step of confirming the screening time segment in the patient weight time sequence corresponding to the historical information based on the preset sliding window and taking the diseased weight group as the starting point to obtain a first update time segment; obtain a first updated weight variance based on the first update time segment; if the first updated weight variance is greater than or equal to the screening variance threshold, obtain a first evaluation time segment based on the first update time segment and the screening time segment, wherein the first evaluation time segment is the complement of the screening time segment in the first update time segment; the first evaluation time segment includes patient weight groups whose number is the sliding step; obtain the patient weight mean and the measurement time mean according to the patient weight groups in the first evaluation time segment, wherein the patient weight mean and the measurement time mean are the mean of the patient weight and the mean of the patient measurement time in the multiple patient weight groups corresponding to the first evaluation time segment, respectively;

[0029] Based on the patient weight mean, measurement time mean, diseased weight group and preset weight change relationship, the weight change rate is calculated, and one or more target information sets are obtained using the weight change rate.

[0030] Optionally, the weight change relationship is as follows:

[0031]

[0032] Wherein, V represents the weight change rate, W1 represents the weight of patients in the diseased weight group, W0 represents the mean weight of patients, T1 represents the measurement time of patients in the diseased weight group, and T0 represents the mean measurement time.

[0033] Optionally, the obtaining one or more target information sets by using the weight change rate includes:

[0034] An absolute value operation is performed on the weight change rate to obtain a first weight change rate, and the first weight change rate is compared with a preset weight screening threshold value. If the first weight change rate is greater than or equal to the weight screening threshold value, the first update window is used as the sliding window, and the step of updating the sliding window using a preset sliding step length is returned to obtain a second update window, and a second update time segment is obtained using the second update window, and a second updated weight variance is obtained based on the second update time segment. If the second updated weight variance is greater than or equal to the screening variance threshold value, a second evaluation time segment is obtained based on the second update time segment and the first update time segment, and a second weight change rate is obtained using the second evaluation time segment;

[0035] Obtaining a weight change difference using the first weight change rate and the second weight change rate, wherein the weight change difference is an absolute difference between the first weight change rate and the second weight change rate;

[0036] comparing the weight change difference with a preset weight change threshold;

[0037] If the weight change difference is greater than the weight change threshold, the second update window is used as the sliding window, and the process returns to the step of updating the sliding window using a preset sliding step length;

[0038] If the weight change difference is less than or equal to the weight change threshold, the patient weight range is determined based on the second update time sequence, wherein the patient weight range has the largest patient weight in the second update time sequence as the maximum value and the smallest patient weight as the minimum value;

[0039] The screening weight ranges are constructed based on the target weights in the target weight group, where the screening weight ranges are as follows:

[0040] F=(αw,βw)

[0041] Wherein, F represents the screening weight range, α and β are preset coefficients, and w is the target weight;

[0042] Determine whether the screening weight range is a subset of the patient's weight range;

[0043] If the screened weight range is a subset of the patient's weight range, the historical information corresponding to the patient's weight range is retained; otherwise, the historical information corresponding to the patient's weight range is discarded, the retained historical information is aggregated to obtain a target information set, and the target information set is aggregated to obtain one or more target information sets.

[0044] Optionally, using the target weight time series to identify a predicted disease sequence in one or more target information sets includes:

[0045] For each of one or more target information sets, the following operations are performed:

[0046] The following operations are performed for each historical information in the target information set:

[0047] Using the patient weight range corresponding to the historical information, the initial illness time and the confirmed illness time are confirmed in the patient weight time series, wherein the initial illness time and the confirmed illness time are the patient measurement time corresponding to the first patient weight group and the patient measurement time corresponding to the last patient weight group in the second update time series segment, respectively;

[0048] According to the initial illness time and the confirmed illness time, the initial illness weight and the confirmed illness weight are determined within the illness weight range, wherein the initial illness weight corresponds to the initial illness time, and the confirmed illness time corresponds to the confirmed illness weight;

[0049] Obtain reference weight change rate based on initial illness time, initial illness weight, confirmed illness time and confirmed illness weight;

[0050] Based on the initial illness time and the confirmed illness time, the latent time is obtained, wherein the latent time is the absolute difference between the initial illness time and the confirmed illness time. The latent time is used to retrieve a retrieval weight group in the target weight time series with the target weight group as the starting point, wherein the retrieval weight group includes the retrieval weight and the retrieval collection time, and the target weight change rate is obtained using the retrieval weight group and the target weight group;

[0051] comparing the reference weight change rate with the target weight change rate;

[0052] If the reference weight change rate and the target weight change rate are both greater than 0, and the reference weight change rate is greater than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded;

[0053] If the reference weight change rate and the target weight change rate are both less than 0, and the reference weight change rate is less than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded;

[0054] The retained historical information is aggregated to obtain an updated information set, the updated information sets are aggregated to obtain one or more updated information sets, and a predicted disease sequence is confirmed based on the one or more updated information sets.

[0055] Optionally, confirming a predicted disease sequence based on the one or more updated information sets comprises:

[0056] For each of the one or more update information sets, perform the following operations:

[0057] The following operations are performed for each historical information in the update information set:

[0058] The diseased facial temperature point set is obtained by using the confirmed disease time, wherein the diseased facial temperature point set includes multiple diseased facial temperatures, and the diseased facial temperatures correspond to the target facial temperatures one by one, and the diseased facial temperatures in the diseased facial temperature point set are respectively summarized according to the facial acupoints to obtain multiple diseased acupoint temperature sets, wherein the diseased acupoint temperature set includes multiple diseased acupoint temperatures, and the following operations are performed on each of the multiple diseased acupoint temperature sets:

[0059] Obtaining an acupoint temperature mean based on the diseased acupoint temperature set, wherein the acupoint temperature mean is the mean of temperatures of multiple diseased acupoints in the diseased acupoint temperature set, and summarizing the acupoint temperature means to obtain an acupoint temperature mean set;

[0060] Based on the update information set, an updated age mean is obtained, wherein the updated age mean is the mean of the patient age corresponding to each of the multiple historical information corresponding to the update information set; using the update information set, an updated weight change rate set is obtained, wherein the updated weight change rate set includes multiple updated weight change rates, and the updated weight change rates correspond to the historical information in the update information set one by one; based on the updated weight change rate set, an updated weight change mean is obtained, wherein the updated weight change mean is the mean of the multiple updated weight change rates in the updated weight change rate set;

[0061] The user age of the smart scale is obtained, and a disease prediction matrix is ​​constructed based on the user age, acupoint temperature mean set, updated age mean, and updated weight change mean. The disease prediction matrix is ​​as follows:

[0062]

[0063] Among them, Q represents the disease prediction matrix, h0 represents the use age, v0 represents the target weight change rate, y1, t2, t n They represent the first target facial temperature, the second target facial temperature and the nth target facial temperature in the target facial temperature point set, respectively. h1 and v1 represent the updated age mean and updated weight change mean corresponding to the first updated information set in one or more updated information sets, respectively. t 11 ,t 12 ,t 1n They represent the first acupoint temperature mean, the second acupoint temperature mean and the nth acupoint temperature mean in the acupoint temperature mean set respectively, and u represents a total of u updated information sets;

[0064] Calculating disease prediction values ​​using a disease prediction matrix and a pre-constructed disease prediction relationship, summarizing the disease prediction values ​​to obtain a disease prediction value set, and performing a sorting operation on the disease prediction values ​​in the disease prediction value set in ascending order to obtain an initial disease prediction sequence;

[0065] Using a preset disease prediction threshold, a target disease sequence is identified in an initial disease prediction sequence, wherein the disease prediction values ​​in the target disease sequence are all less than or equal to the disease prediction threshold, and a predicted disease sequence is obtained based on the target disease sequence.

[0066] Optionally, the disease prediction relationship is as follows:

[0067]

[0068] Among them, Y represents the disease prediction value, ω, They are all preset coefficients, j represents the element in the j-th row in the disease prediction matrix, and j is an integer greater than or equal to 2 and less than or equal to u.

[0069] To achieve the above object, the present invention also provides a disease prediction system for a smart scale, comprising:

[0070] A prediction environment confirmation module, used to receive a prediction instruction and confirm a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit and a facial temperature detection unit;

[0071] A user information collection module, used to confirm receiving a data collection instruction from a data collection unit, and to obtain a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time;

[0072] Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups;

[0073] A reference information acquisition module, used to identify a target data group in the second data group sequence using the target facial image corresponding to the detection information, and to update a reference weight time series corresponding to the target data group using the target weight group corresponding to the detection information to obtain a target weight time series;

[0074] Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time;

[0075] A user information analysis module, used to obtain one or more target information sets based on the historical information set;

[0076] The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

[0077] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0078] A memory storing at least one instruction; and a processor executing the instruction stored in the memory to implement the above-mentioned disease prediction method for smart scale.

[0079] In order to solve the above problem, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned disease prediction method for a smart scale.

[0080] The present invention is to solve the problem described in the background technology. The present invention obtains a first data set based on the data collection instruction, wherein the first data set includes multiple first data sets, and the first data set includes a reference facial image, a reference fingerprint image and a reference weight time series, wherein the reference weight time series includes multiple reference weight groups, and the reference weight group is composed of a reference weight and a measurement time, and the detection information is obtained by using a smart scale after startup, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes multiple target facial temperatures, and based on the target fingerprint image corresponding to the detection information, a second data set sequence is confirmed in the first data set, wherein the second data set sequence includes one or more second data sets. It can be seen that the present invention takes into account the error when only facial images are used for recognition, therefore, fingerprint recognition and facial recognition are combined, and different resources required for different recognition methods are considered before recognition, therefore, the fingerprint recognition method is first adopted, and here the target fingerprint image is used to obtain the second data set sequence in the first data set. The second data group sequence is confirmed in the data set, and then, the target facial image is used to confirm the target data group in the second data group sequence to improve the accuracy of confirming the target data group, and the historical information set is obtained by using the data analysis instruction, wherein the historical information set includes multiple patient information, wherein the patient information includes the disease name, the patient age and the patient weight time series, wherein the patient weight time series includes multiple patient weight groups, and the patient weight group includes the patient weight and the patient measurement time, and one or more target information sets are obtained based on the historical information set, and the target weight time series is used to confirm the predicted disease sequence in one or more target information sets. It can be seen that the present invention screens the historical information set from different angles, so that the screened historical information set can better characterize the characteristics of the smart scale user, and the parameters for realizing disease prediction are obtained through the screened updated information set, and the disease prediction matrix is ​​constructed using the parameters, and the similarity between the relevant information of the smart scale user and the relevant information of the patient corresponding to a certain type of disease is calculated through the disease prediction matrix, and the disease prediction value is obtained, and the disease prediction value is used to predict the disease suffered by the smart scale user. Therefore, the present invention can realize the prediction of the disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 A schematic diagram of a flow chart of a disease prediction method for a smart scale provided in one embodiment of the present invention;

[0082] Figure 2 A functional module diagram of a disease prediction system for a smart scale provided by an embodiment of the present invention;

[0083] Figure 3A schematic diagram of the structure of an electronic device for implementing the disease prediction method for a smart scale provided in one embodiment of the present invention.

[0084] Description of reference numerals:

[0085] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0086] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0087] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0088] The embodiment of the present application provides a disease prediction method for a smart scale. The execution subject of the disease prediction method for a smart scale includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the disease prediction method for a smart scale can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0089] Reference Figure 1 FIG. 1 is a flow chart of a disease prediction method for a smart scale provided by an embodiment of the present invention. In this embodiment, the disease prediction method for a smart scale includes:

[0090] S1. Receive a prediction instruction, and confirm a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit, and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit, and a facial temperature detection unit.

[0091] It should be explained that the prediction instruction is an instruction issued by the user of the smart scale, and the prediction instruction is used to predict whether the user has a disease in combination with the weight change of the user of the smart scale. The prediction environment refers to the necessary environment for realizing disease prediction of the user, and the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit and a prediction feedback unit, and the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit and a facial temperature detection unit. For the specific application of the units, please refer to the subsequent embodiments. The prediction system refers to an APP or applet used to predict the disease of the user. By combining the weight information of the user transmitted by the smart scale, data analysis can be performed, and then, prediction of whether the user has a disease can be realized. The present invention can realize disease prediction for users of smart scales.

[0092] For example, in order to predict weight-related diseases, a number of hospitals have jointly developed a prediction system, and the prediction system can be combined with a smart scale to analyze and store the information generated by the smart scale user when using the smart scale. When Xiao Zhang uses the smart scale, the smart scale imports Xiao Zhang's weight and time information when weighing into the prediction system. The prediction system combines big data and Xiao Zhang's previous weight and time information to predict the disease Xiao Zhang suffers from.

[0093] S2. Confirm receipt of a data collection instruction from a data collection unit, and obtain a first data set based on the data collection instruction, wherein the first data set includes multiple first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes multiple reference weight groups, and the reference weight group consists of a reference weight and a measurement time.

[0094] It is understandable that the first data group refers to data stored in advance in the prediction system. The reference facial image and the reference fingerprint image are respectively used to identify the facial image and the fingerprint image of the user of the smart scale. Optionally, the fingerprint image can be a fingerprint image of the thumb. The reference weight refers to the weight measured by the user of the smart scale when using the smart scale. The measurement time refers to the time when the user of the smart scale uses the smart scale to measure the weight. For example: the smart scale is a household smart scale. In order to predict whether each family member suffers from a disease, the reference facial image and the reference fingerprint image of each family member are collected in advance, and when each family member uses the smart scale, the measured reference weight and measurement time are stored in the order of measurement time from the earliest to the latest to obtain the reference weight time sequence of the family member.

[0095] S3, confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups.

[0096] It is understandable that the method of obtaining the detection information by using the activated smart scale includes:

[0097] The target weight is obtained based on the weight collection unit, and the time of obtaining the target weight is recorded to obtain the weight collection time, and the target fingerprint image and the target facial image are obtained by using the fingerprint collection unit and the facial collection unit respectively;

[0098] Acquire a target facial temperature point set using a facial temperature detection unit and a pre-constructed facial acupoint set, wherein the facial acupoint set includes a plurality of facial acupoints, and the facial acupoints correspond one-to-one to the target facial temperature;

[0099] The target weight, weight collection time, target fingerprint image, target facial image and target facial temperature point set are summarized to obtain the detection information.

[0100] It should be explained that the target weight refers to the weight of the person using the smart scale, and the weight collection time refers to the time when the person using the smart scale weighs himself. The target facial image and the target fingerprint image have the same effect as the reference facial image and the reference fingerprint image, which will not be repeated here. The facial acupoint set refers to a collection of facial acupoints. Optionally, the facial acupoint set is obtained through a facial acupoint map. Optionally, an infrared thermometer and a facial acupoint set are used to obtain the facial temperature point set. Other technologies can achieve the same effect, which will not be repeated here.

[0101] Further, the step of identifying a second data set sequence in the first data set based on the target fingerprint image corresponding to the detection information includes:

[0102] Extracting first data groups from the first data group set in sequence, and performing the following operations on the extracted first data groups:

[0103] Acquire fingerprint similarities between a reference fingerprint image and a target fingerprint image in the first data group, and summarize the fingerprint similarities to obtain a fingerprint similarity set;

[0104] Sorting the fingerprint similarities in the fingerprint similarity set in descending order of fingerprint similarity to obtain an initial fingerprint similarity sequence;

[0105] A target fingerprint similarity sequence is obtained using a preset first screening value and an initial fingerprint similarity sequence, wherein the fingerprint similarities in the target fingerprint similarity sequence are all greater than or equal to the first screening value, and a second data group sequence is confirmed based on the target fingerprint similarity sequence, wherein the second data groups in the second data group sequence correspond one-to-one to the target fingerprint similarities in the target fingerprint similarity sequence.

[0106] It should be understood that the fingerprint similarity refers to the similarity between the reference fingerprint image and the target fingerprint image. Optionally, the similarity between the reference fingerprint image and the target fingerprint image is obtained using a similarity clustering method. The same effect can be achieved using other methods, which will not be repeated here. Exemplarily, the first data set includes a total of 3 first data sets, and the fingerprint similarities obtained using the first data set and the target fingerprint image are: 0.9, 0.7 and 0.8, respectively. The initial fingerprint similarity sequence is: 0.9, 0.8 and 0.7, and the first screening value is 0.75. The target fingerprint similarity sequence obtained using the first screening value and the initial fingerprint similarity sequence is 0.9 and 0.8, and the second data set sequence is composed of the first data set corresponding to 0.9 and the first data set corresponding to 0.8.

[0107] S4. Using the target facial image corresponding to the detection information, identify the target data group in the second data group sequence, and use the target weight group corresponding to the detection information to update the reference weight time series corresponding to the target data group to obtain the target weight time series.

[0108] It should be explained that the method for obtaining the target data group is: extracting the second data group from the second data group sequence in sequence, and using the reference facial image and the target facial image in the extracted second data group to obtain facial similarity, summarizing the facial similarity to obtain a facial similarity set, and taking the second data group corresponding to the largest facial similarity in the facial similarity set as the target data group, wherein the method for obtaining facial similarity is the same as the method for obtaining fingerprint similarity and can achieve the same effect, which will not be repeated here.

[0109] It should be understood that the computing resources required for calculating fingerprint similarity are less than those required for calculating facial similarity. Therefore, in the embodiment of the present invention, the first data set is first screened using fingerprint similarity. Since there may be errors when using fingerprint similarity for judgment, facial similarity is used to screen the second data set in the second data set sequence to obtain the target data set, that is, the set of data stored by the smart scale user when previously using the smart scale.

[0110] It should be explained that the target weight group corresponding to the detection information is used to update the reference weight time series corresponding to the target data group to obtain the target weight time series, which means that the target weight group is added to the reference weight time series in order from earliest to latest to obtain the target weight time series.

[0111] S5. Confirm receipt of the data analysis instruction from the data analysis unit, and use the data analysis instruction to obtain a historical information set, wherein the historical information set includes multiple patient information, wherein the patient information includes disease name, patient age and patient weight time series, wherein the patient weight time series includes multiple patient weight groups, and the patient weight group includes patient weight and patient measurement time.

[0112] It should be explained that the patient information refers to the information of the confirmed patients, the disease name refers to the name of the disease diagnosed by the patient, the patient age refers to the age of the patient, and the patient weight time series refers to the time series of the patient's weight until the patient is diagnosed with the disease. The patient weight time series has the same definition as the reference weight time series, which will not be repeated here. The difference between the patient weight time series and the reference weight time series is that the patient weight time series contains information that can express the changing trend of weight when suffering from the disease. For example, patients with hypothyroidism will show an upward trend in weight over a period of time. Patient weight refers to the patient's weight, and patient measurement time refers to the time when the patient's weight is measured.

[0113] S6. Obtain one or more target information sets based on the historical information sets.

[0114] Further, the acquiring one or more target information sets based on the historical information sets includes:

[0115] According to the disease names corresponding to the historical information in the historical information set, the historical information is aggregated to obtain one or more initial information sets;

[0116] For each of the one or more initial information sets, the following operations are performed:

[0117] The following operations are performed for each historical information in the initial information set:

[0118] The last patient weight group is identified in the patient weight time series corresponding to the historical information to obtain the diseased weight group, and a screening time series segment is identified in the patient weight time series corresponding to the historical information based on a preset sliding window and taking the diseased weight group as a starting point, wherein the screening time series segment includes multiple screening weight groups, and the screening weight variance is obtained based on the multiple screening weight groups corresponding to the screening time series segment, wherein the screening weight variance is the variance of the patient weight corresponding to the multiple screening weight groups;

[0119] Compare the screening weight variance with a preset screening variance threshold; if the screening weight variance is greater than or equal to the screening variance threshold, update the sliding window using a preset sliding step to obtain a first update window; take the first update window as the sliding window, return to the step of confirming the screening time segment in the patient weight time sequence corresponding to the historical information based on the preset sliding window and taking the diseased weight group as the starting point to obtain a first update time segment; obtain a first updated weight variance based on the first update time segment; if the first updated weight variance is greater than or equal to the screening variance threshold, obtain a first evaluation time segment based on the first update time segment and the screening time segment, wherein the first evaluation time segment is the complement of the screening time segment in the first update time segment; the first evaluation time segment includes patient weight groups whose number is the sliding step; obtain the patient weight mean and the measurement time mean according to the patient weight groups in the first evaluation time segment, wherein the patient weight mean and the measurement time mean are the mean of the patient weight and the mean of the patient measurement time in the multiple patient weight groups corresponding to the first evaluation time segment, respectively;

[0120] Based on the patient weight mean, measurement time mean, diseased weight group and preset weight change relationship, the weight change rate is calculated, and one or more target information sets are obtained using the weight change rate.

[0121] It should be explained that the collected historical information may be information of different disease names. Therefore, the historical information can be summarized according to the disease name to obtain the historical information of the same disease, wherein the collection of historical information of the same disease constitutes the initial information set. Optionally, the sliding window is a fixed sliding window. For example: the patient weight time series includes: (1, 45), (3, 47), (8, 51), (9, 50) and (15, 47), wherein 1, 3, 8, 9 and 15 are all patient measurement times in the patient weight group, 45, 47, 51, 50 and 47 are all patient weights in the patient weight group, then (15, 47) is the diseased weight group, the sliding window is 3, then the screening time series segments confirmed in the patient weight time series are: (8, 51), (9, 50) and (15, 47).

[0122] It should be understood that when the screening weight variance is greater than or equal to the screening variance threshold, it indicates that the patient has a large weight change in the screening time segment, that is, the patient may have been ill or the weight change has occurred due to the illness. Since the set sliding window may not be able to retrieve the weight change of the patient at the beginning of the illness, the sliding window is updated, that is, the range of the sliding window is expanded, for example: the size of the sliding window is 3, the sliding step is 2, and the size of the first update window is 5, the first update time segment is obtained in the same way as the screening time segment, and the first update weight variance is obtained in the same way as the screening weight variance. For example: the patient weight time series includes: (1, 45), (2, 46), (3, 47), (8, 51), (9, 50) and (15, 47), the sliding window is 3, then the screening time series segments are: (8, 51), (9, 50) and (15, 47), the sliding step is 2, then the first update time series segment is (2, 46), (3, 47), (8, 51), (9, 50) and (15, 47), and the first judgment time series segment is (2, 46), (3, 47).

[0123] Furthermore, the weight change relationship is as follows:

[0124]

[0125] Wherein, V represents the weight change rate, W1 represents the weight of patients in the diseased weight group, W0 represents the mean weight of patients, T1 represents the measurement time of patients in the diseased weight group, and T0 represents the mean measurement time.

[0126] It should be understood that the variance can be used to show the overall change trend of the patient's weight time series, that is, the overall characteristics of the patient's weight change, but it cannot show the local characteristics of the patient's weight time series. Therefore, the weight change rate is calculated to characterize the local characteristics of the patient's weight change.

[0127] It should be explained that the method of obtaining one or more target information sets by using the weight change rate includes:

[0128] An absolute value operation is performed on the weight change rate to obtain a first weight change rate, and the first weight change rate is compared with a preset weight screening threshold value. If the first weight change rate is greater than or equal to the weight screening threshold value, the first update window is used as the sliding window, and the step of updating the sliding window using a preset sliding step length is returned to obtain a second update window, and a second update time segment is obtained using the second update window, and a second updated weight variance is obtained based on the second update time segment. If the second updated weight variance is greater than or equal to the screening variance threshold value, a second evaluation time segment is obtained based on the second update time segment and the first update time segment, and a second weight change rate is obtained using the second evaluation time segment;

[0129] Obtaining a weight change difference using the first weight change rate and the second weight change rate, wherein the weight change difference is an absolute difference between the first weight change rate and the second weight change rate;

[0130] comparing the weight change difference with a preset weight change threshold;

[0131] If the weight change difference is greater than the weight change threshold, the second update window is used as the sliding window, and the process returns to the step of updating the sliding window using a preset sliding step length;

[0132] If the weight change difference is less than or equal to the weight change threshold, the patient weight range is determined based on the second update time sequence, wherein the patient weight range has the largest patient weight in the second update time sequence as the maximum value and the smallest patient weight as the minimum value;

[0133] The screening weight ranges are constructed based on the target weights in the target weight group, where the screening weight ranges are as follows:

[0134] F=(αw,βw)

[0135] Wherein, F represents the screening weight range, α and β are preset coefficients, and w is the target weight;

[0136] Determine whether the screening weight range is a subset of the patient's weight range;

[0137] If the screened weight range is a subset of the patient's weight range, the historical information corresponding to the patient's weight range is retained; otherwise, the historical information corresponding to the patient's weight range is discarded, the retained historical information is aggregated to obtain a target information set, and the target information set is aggregated to obtain one or more target information sets.

[0138] It is understandable that when the first weight change rate is greater than or equal to the weight screening threshold, it indicates that the patient's weight has changed significantly. The difference between the second update window and the first update window is that the second update window adds a sliding step size on the basis of the first update window. For example: the size of the first update window is 5, the sliding step size is 2, and the size of the second update window is 7. The acquisition method of the second update time segment is the same as the acquisition method of the first update time segment. The acquisition method of the second updated weight variance is the same as the acquisition method of the first updated weight variance. The acquisition method of the second judgment time segment is the same as the acquisition method of the first judgment time segment. The second weight change rate is the same as the acquisition method of the weight change rate. When the weight change difference is greater than the weight change threshold, it indicates that there is a large difference between the second judgment time segment and the first judgment time segment, that is, the patient still has a large weight change. Therefore, the second update time segment obtained still cannot characterize the weight change of the patient when he just became ill, so the second update time segment is updated until the weight change difference is less than or equal to the weight change threshold.

[0139] It should be explained that the patient's weight is not only affected by the disease, but also by the environment, temperature, diet, etc. The purpose of taking the largest patient weight in the second update period as the maximum value and the smallest patient weight as the minimum value is to reduce the impact of factors such as the environment. When the weight range is selected as a subset of the patient's weight range, it indicates that the historical information can more accurately express the user's weight changes, thereby improving the accuracy of disease prediction for smart scale users.

[0140] S7. Using the target weight time series, a predicted disease sequence is identified in one or more target information sets, and based on the prediction feedback unit, the predicted disease sequence is sent to an initiator of the prediction instruction to achieve disease prediction.

[0141] Further, the use of the target weight time series to identify a predicted disease sequence in one or more target information sets includes:

[0142] For each of one or more target information sets, the following operations are performed:

[0143] The following operations are performed for each historical information in the target information set:

[0144] Using the patient weight range corresponding to the historical information, the initial illness time and the confirmed illness time are confirmed in the patient weight time series, wherein the initial illness time and the confirmed illness time are the patient measurement time corresponding to the first patient weight group and the patient measurement time corresponding to the last patient weight group in the second update time series segment, respectively;

[0145] According to the initial illness time and the confirmed illness time, the initial illness weight and the confirmed illness weight are determined within the illness weight range, wherein the initial illness weight corresponds to the initial illness time, and the confirmed illness time corresponds to the confirmed illness weight;

[0146] Obtain reference weight change rate based on initial illness time, initial illness weight, confirmed illness time and confirmed illness weight;

[0147] Based on the initial illness time and the confirmed illness time, the latent time is obtained, wherein the latent time is the absolute difference between the initial illness time and the confirmed illness time. The latent time is used to retrieve a retrieval weight group in the target weight time series with the target weight group as the starting point, wherein the retrieval weight group includes the retrieval weight and the retrieval collection time, and the target weight change rate is obtained using the retrieval weight group and the target weight group;

[0148] comparing the reference weight change rate with the target weight change rate;

[0149] If the reference weight change rate and the target weight change rate are both greater than 0, and the reference weight change rate is greater than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded;

[0150] If the reference weight change rate and the target weight change rate are both less than 0, and the reference weight change rate is less than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded;

[0151] The retained historical information is aggregated to obtain an updated information set, the updated information sets are aggregated to obtain one or more updated information sets, and a predicted disease sequence is confirmed based on the one or more updated information sets.

[0152] It is understandable that the method for obtaining the reference weight change rate based on the initial illness time, initial illness weight, confirmed illness time and confirmed illness weight is the same as the method for obtaining the weight change rate, and will not be repeated here. The retrieval weight group refers to the reference weight group with the smallest absolute difference between the retrieval collection time corresponding to the retrieval weight group and the weight collection time corresponding to the target weight group. The method for obtaining the target weight change rate using the retrieval weight group and the target weight group is the same as the method for obtaining the weight change rate.

[0153] It should be understood that illness may cause weight gain or weight loss. If weight will increase, the reference weight change rate and the target weight change rate will both be greater than 0. On the contrary, when weight will increase, the rate of weight gain may increase faster and faster due to the aggravation of the illness. When weight will decrease, the rate of weight loss may increase faster and faster due to the aggravation of the illness. Therefore, when the reference weight change rate and the target weight change rate are both greater than 0, and the reference weight change rate is greater than or equal to the target weight change rate, or the reference weight change rate and the target weight change rate are both less than 0, and the reference weight change rate is less than or equal to the target weight change rate, it can be determined that the historical information has reference value for predicting diseases for smart scale users.

[0154] It should be explained that the step of confirming the predicted disease sequence based on the one or more updated information sets includes:

[0155] For each of the one or more update information sets, perform the following operations:

[0156] The following operations are performed for each historical information in the update information set:

[0157] The diseased facial temperature point set is obtained by using the confirmed disease time, wherein the diseased facial temperature point set includes multiple diseased facial temperatures, and the diseased facial temperatures correspond to the target facial temperatures one by one, and the diseased facial temperatures in the diseased facial temperature point set are respectively summarized according to the facial acupoints to obtain multiple diseased acupoint temperature sets, wherein the diseased acupoint temperature set includes multiple diseased acupoint temperatures, and the following operations are performed on each of the multiple diseased acupoint temperature sets:

[0158] Obtaining an acupoint temperature mean based on the diseased acupoint temperature set, wherein the acupoint temperature mean is the mean of temperatures of multiple diseased acupoints in the diseased acupoint temperature set, and summarizing the acupoint temperature means to obtain an acupoint temperature mean set;

[0159] Based on the update information set, an updated age mean is obtained, wherein the updated age mean is the mean of the patient age corresponding to each of the multiple historical information corresponding to the update information set; using the update information set, an updated weight change rate set is obtained, wherein the updated weight change rate set includes multiple updated weight change rates, and the updated weight change rates correspond to the historical information in the update information set one by one; based on the updated weight change rate set, an updated weight change mean is obtained, wherein the updated weight change mean is the mean of the multiple updated weight change rates in the updated weight change rate set;

[0160] The user age of the smart scale is obtained, and a disease prediction matrix is ​​constructed based on the user age, acupoint temperature mean set, updated age mean, and updated weight change mean. The disease prediction matrix is ​​as follows:

[0161]

[0162] Among them, Q represents the disease prediction matrix, h0 represents the use age, v0 represents the target weight change rate, t1, t2, t n They represent the first target facial temperature, the second target facial temperature and the nth target facial temperature in the target facial temperature point set, respectively. h1 and v1 represent the updated age mean and updated weight change mean corresponding to the first updated information set in one or more updated information sets, respectively. t 11 ,t 12 ,t 1n They represent the first acupoint temperature mean, the second acupoint temperature mean and the nth acupoint temperature mean in the acupoint temperature mean set respectively, and u represents a total of u updated information sets;

[0163] Calculating disease prediction values ​​using a disease prediction matrix and a pre-constructed disease prediction relationship, summarizing the disease prediction values ​​to obtain a disease prediction value set, and performing a sorting operation on the disease prediction values ​​in the disease prediction value set in ascending order to obtain an initial disease prediction sequence;

[0164] Using a preset disease prediction threshold, a target disease sequence is identified in an initial disease prediction sequence, wherein the disease prediction values ​​in the target disease sequence are all less than or equal to the disease prediction threshold, and a predicted disease sequence is obtained based on the target disease sequence.

[0165] It should be understood that the diseased facial temperature point set refers to the set of facial temperatures of multiple patients when the time is the confirmed time, and the method of obtaining the patient facial temperature point set is the same as the method of obtaining the target facial temperature point set, which will not be repeated here. Therefore, there is a one-to-one correspondence between the diseased facial temperature and the target facial temperature on the acupoints, and the diseased acupoint temperature set refers to the set of temperatures corresponding to the diseased facial temperature point corresponding to each historical information in the updated information set at the same facial acupoint, wherein the temperature corresponding to the facial acupoint is the diseased acupoint temperature. The method of obtaining the updated weight change rate is the same as the method of obtaining the weight change rate, which will not be repeated here.

[0166] It is understandable that the smaller the disease prediction value is, the greater the possibility that the smart scale user suffers from the disease corresponding to the updated information set. The predicted disease sequence is a sequence arranged according to the disease names corresponding to the disease prediction values. For example: the target disease sequences are: 0.02, 0.1, 0.3, and the disease names corresponding to 0.02, 0.1, 0.3 are respectively type A disease, type B disease and type C disease, then the predicted disease sequence is: type A disease, type B disease and type C disease.

[0167] It should be explained that the disease prediction relationship is as follows:

[0168]

[0169] Among them, Y represents the disease prediction value, ω, They are all preset coefficients, j represents the element in the j-th row in the disease prediction matrix, and j is an integer greater than or equal to 2 and less than or equal to u.

[0170] The present invention is to solve the problem described in the background technology. The present invention obtains a first data set based on the data collection instruction, wherein the first data set includes multiple first data sets, and the first data set includes a reference facial image, a reference fingerprint image and a reference weight time series, wherein the reference weight time series includes multiple reference weight groups, and the reference weight group is composed of a reference weight and a measurement time, and the detection information is obtained by using a smart scale after startup, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes multiple target facial temperatures, and based on the target fingerprint image corresponding to the detection information, a second data set sequence is confirmed in the first data set, wherein the second data set sequence includes one or more second data sets. It can be seen that the present invention takes into account the error when only facial images are used for recognition, therefore, fingerprint recognition and facial recognition are combined, and different resources required for different recognition methods are considered before recognition, therefore, the fingerprint recognition method is first adopted, and here the target fingerprint image is used to obtain the second data set sequence in the first data set. The second data group sequence is confirmed in the data set, and then, the target facial image is used to confirm the target data group in the second data group sequence to improve the accuracy of confirming the target data group, and the historical information set is obtained by using the data analysis instruction, wherein the historical information set includes multiple patient information, wherein the patient information includes the disease name, the patient age and the patient weight time series, wherein the patient weight time series includes multiple patient weight groups, and the patient weight group includes the patient weight and the patient measurement time, and one or more target information sets are obtained based on the historical information set, and the target weight time series is used to confirm the predicted disease sequence in one or more target information sets. It can be seen that the present invention screens the historical information set from different angles, so that the screened historical information set can better characterize the characteristics of the smart scale user, and the parameters for realizing disease prediction are obtained through the screened updated information set, and the disease prediction matrix is ​​constructed using the parameters, and the similarity between the relevant information of the smart scale user and the relevant information of the patient corresponding to a certain type of disease is calculated through the disease prediction matrix, and the disease prediction value is obtained, and the disease prediction value is used to predict the disease suffered by the smart scale user. Therefore, the present invention can realize the prediction of the disease.

[0171] like Figure 2 , which is a functional module diagram of a disease prediction system for a smart scale provided by an embodiment of the present invention.

[0172] The disease prediction system 100 for smart scales of the present invention can be installed in an electronic device. According to the functions to be implemented, the disease prediction system 100 for smart scales can include a prediction environment confirmation module 101, a user information collection module 102, a reference information acquisition module 103 and a user information analysis module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0173] The prediction environment confirmation module 101 is used to receive the prediction instruction and confirm the prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit and a facial temperature detection unit;

[0174] The user information acquisition module 102 is used to confirm receiving a data collection instruction from a data collection unit, and acquire a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time;

[0175] Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups;

[0176] The reference information acquisition module 103 is used to identify the target data group in the second data group sequence using the target facial image corresponding to the detection information, and to update the reference weight time series corresponding to the target data group using the target weight group corresponding to the detection information to obtain the target weight time series;

[0177] Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time;

[0178] The user information analysis module 104 is used to obtain one or more target information sets based on the historical information set;

[0179] The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

[0180] In detail, each module in the disease prediction system 100 for smart scales in the embodiment of the present invention is used in the same manner as described above. Figure 1 The disease prediction method for smart scales described in the present invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0181] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a disease prediction method for a smart scale provided by an embodiment of the present invention.

[0182] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a disease prediction method program for a smart scale.

[0183] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the disease prediction method program for the smart scale, but also can be used to temporarily store data that has been output or is to be output.

[0184] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as disease prediction method programs for smart scales, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0185] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0186] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0187] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0188] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0189] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0190] The disease prediction method program for the smart scale stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0191] receiving a prediction instruction, and confirming a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit, and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit, and a facial temperature detection unit;

[0192] Confirming receipt of a data collection instruction from a data collection unit, and acquiring a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time;

[0193] Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups;

[0194] Using the target facial image corresponding to the detection information, a target data group is identified in the second data group sequence, and using the target weight group corresponding to the detection information to update the reference weight time series corresponding to the target data group to obtain the target weight time series;

[0195] Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time;

[0196] Acquire one or more target information sets based on the historical information sets;

[0197] The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

[0198] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0199] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0200] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0201] receiving a prediction instruction, and confirming a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit, and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit, and a facial temperature detection unit;

[0202] Confirming receipt of a data collection instruction from a data collection unit, and acquiring a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time;

[0203] Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups;

[0204] Using the target facial image corresponding to the detection information, a target data group is identified in the second data group sequence, and using the target weight group corresponding to the detection information to update the reference weight time series corresponding to the target data group to obtain the target weight time series;

[0205] Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time;

[0206] Acquire one or more target information sets based on the historical information sets;

[0207] The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

[0208] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0209] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0210] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0211] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0212] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A disease prediction method for a smart scale, characterized in that: The method comprises: receiving a prediction instruction, and confirming a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit, and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit, and a facial temperature detection unit; Confirming receipt of a data collection instruction from a data collection unit, and acquiring a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time; Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups; Using the target facial image corresponding to the detection information, a target data group is identified in the second data group sequence, and using the target weight group corresponding to the detection information to update the reference weight time series corresponding to the target data group to obtain the target weight time series; Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time; Acquire one or more target information sets based on the historical information sets; The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

2. The disease prediction method for a smart scale according to claim 1, characterized in that: The method of obtaining detection information by using the activated smart scale includes: The target weight is obtained based on the weight collection unit, and the time of obtaining the target weight is recorded to obtain the weight collection time, and the target fingerprint image and the target facial image are obtained by using the fingerprint collection unit and the facial collection unit respectively; Acquire a target facial temperature point set using a facial temperature detection unit and a pre-constructed facial acupoint set, wherein the facial acupoint set includes a plurality of facial acupoints, and the facial acupoints correspond one-to-one to the target facial temperature; The target weight, weight collection time, target fingerprint image, target facial image and target facial temperature point set are summarized to obtain the detection information.

3. The disease prediction method for a smart scale according to claim 2, characterized in that: The step of identifying a second data set sequence in the first data set based on the target fingerprint image corresponding to the detection information includes: Extracting first data groups from the first data group set in sequence, and performing the following operations on the extracted first data groups: Acquire fingerprint similarities between a reference fingerprint image and a target fingerprint image in the first data group, and summarize the fingerprint similarities to obtain a fingerprint similarity set; Sorting the fingerprint similarities in the fingerprint similarity set in descending order of fingerprint similarity to obtain an initial fingerprint similarity sequence; A target fingerprint similarity sequence is obtained using a preset first screening value and an initial fingerprint similarity sequence, wherein the fingerprint similarities in the target fingerprint similarity sequence are all greater than or equal to the first screening value, and a second data group sequence is confirmed based on the target fingerprint similarity sequence, wherein the second data groups in the second data group sequence correspond one-to-one to the target fingerprint similarities in the target fingerprint similarity sequence.

4. The disease prediction method for a smart scale according to claim 3, characterized in that: The acquiring one or more target information sets based on the historical information sets includes: According to the disease names corresponding to the historical information in the historical information set, the historical information is aggregated to obtain one or more initial information sets; For each of the one or more initial information sets, the following operations are performed: The following operations are performed for each historical information in the initial information set: The last patient weight group is identified in the patient weight time series corresponding to the historical information to obtain the diseased weight group, and a screening time series segment is identified in the patient weight time series corresponding to the historical information based on a preset sliding window and taking the diseased weight group as a starting point, wherein the screening time series segment includes multiple screening weight groups, and the screening weight variance is obtained based on the multiple screening weight groups corresponding to the screening time series segment, wherein the screening weight variance is the variance of the patient weight corresponding to the multiple screening weight groups; Compare the screening weight variance with a preset screening variance threshold; if the screening weight variance is greater than or equal to the screening variance threshold, update the sliding window using a preset sliding step to obtain a first update window; take the first update window as the sliding window, return to the step of confirming the screening time segment in the patient weight time sequence corresponding to the historical information based on the preset sliding window and taking the diseased weight group as the starting point to obtain a first update time segment; obtain a first updated weight variance based on the first update time segment; if the first updated weight variance is greater than or equal to the screening variance threshold, obtain a first evaluation time segment based on the first update time segment and the screening time segment, wherein the first evaluation time segment is the complement of the screening time segment in the first update time segment; the first evaluation time segment includes patient weight groups whose number is the sliding step; obtain the patient weight mean and the measurement time mean according to the patient weight groups in the first evaluation time segment, wherein the patient weight mean and the measurement time mean are the mean of the patient weight and the mean of the patient measurement time in the multiple patient weight groups corresponding to the first evaluation time segment, respectively; Based on the patient weight mean, measurement time mean, diseased weight group and preset weight change relationship, the weight change rate is calculated, and one or more target information sets are obtained using the weight change rate.

5. The disease prediction method for a smart scale according to claim 4, characterized in that: The weight change relationship is as follows: Wherein, V represents the weight change rate, W1 represents the weight of patients in the diseased weight group, W0 represents the mean weight of patients, T1 represents the measurement time of patients in the diseased weight group, and T0 represents the mean measurement time.

6. The disease prediction method for a smart scale according to claim 5, characterized in that: The method of obtaining one or more target information sets by using the weight change rate includes: An absolute value operation is performed on the weight change rate to obtain a first weight change rate, and the first weight change rate is compared with a preset weight screening threshold value. If the first weight change rate is greater than or equal to the weight screening threshold value, the first update window is used as the sliding window, and the step of updating the sliding window using a preset sliding step length is returned to obtain a second update window, and a second update time segment is obtained using the second update window, and a second updated weight variance is obtained based on the second update time segment. If the second updated weight variance is greater than or equal to the screening variance threshold value, a second evaluation time segment is obtained based on the second update time segment and the first update time segment, and a second weight change rate is obtained using the second evaluation time segment; Obtaining a weight change difference using the first weight change rate and the second weight change rate, wherein the weight change difference is an absolute difference between the first weight change rate and the second weight change rate; comparing the weight change difference with a preset weight change threshold; If the weight change difference is greater than the weight change threshold, the second update window is used as the sliding window, and the process returns to the step of updating the sliding window using a preset sliding step length; If the weight change difference is less than or equal to the weight change threshold, the patient weight range is determined based on the second update time sequence, wherein the patient weight range has the largest patient weight in the second update time sequence as the maximum value and the smallest patient weight as the minimum value; The screening weight ranges are constructed based on the target weights in the target weight group, where the screening weight ranges are as follows: F=(αw,βw) Wherein, F represents the screening weight range, α and β are preset coefficients, and w is the target weight; Determine whether the screening weight range is a subset of the patient's weight range; If the screened weight range is a subset of the patient's weight range, the historical information corresponding to the patient's weight range is retained; otherwise, the historical information corresponding to the patient's weight range is discarded, the retained historical information is aggregated to obtain a target information set, and the target information set is aggregated to obtain one or more target information sets.

7. The disease prediction method for a smart scale according to claim 6, characterized in that: The step of using the target weight time series to identify a predicted disease sequence in one or more target information sets includes: For each of one or more target information sets, the following operations are performed: The following operations are performed for each historical information in the target information set: Using the patient weight range corresponding to the historical information, the initial illness time and the confirmed illness time are confirmed in the patient weight time series, wherein the initial illness time and the confirmed illness time are the patient measurement time corresponding to the first patient weight group and the patient measurement time corresponding to the last patient weight group in the second update time series segment, respectively; According to the initial illness time and the confirmed illness time, the initial illness weight and the confirmed illness weight are determined within the illness weight range, wherein the initial illness weight corresponds to the initial illness time, and the confirmed illness time corresponds to the confirmed illness weight; Obtain reference weight change rate based on initial illness time, initial illness weight, confirmed illness time and confirmed illness weight; Based on the initial illness time and the confirmed illness time, the latent time is obtained, wherein the latent time is the absolute difference between the initial illness time and the confirmed illness time. The latent time is used to retrieve a retrieval weight group in the target weight time series with the target weight group as the starting point, wherein the retrieval weight group includes the retrieval weight and the retrieval collection time, and the target weight change rate is obtained using the retrieval weight group and the target weight group; comparing the reference weight change rate with the target weight change rate; If the reference weight change rate and the target weight change rate are both greater than 0, and the reference weight change rate is greater than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded; If the reference weight change rate and the target weight change rate are both less than 0, and the reference weight change rate is less than or equal to the target weight change rate, the historical information is retained, otherwise the historical information is discarded; The retained historical information is aggregated to obtain an updated information set, the updated information sets are aggregated to obtain one or more updated information sets, and a predicted disease sequence is confirmed based on the one or more updated information sets.

8. The disease prediction method for a smart scale according to claim 7, characterized in that: The step of confirming a predicted disease sequence based on the one or more updated information sets comprises: For each of the one or more update information sets, perform the following operations: The following operations are performed for each historical information in the update information set: The diseased facial temperature point set is obtained by using the confirmed disease time, wherein the diseased facial temperature point set includes multiple diseased facial temperatures, and the diseased facial temperatures correspond to the target facial temperatures one by one, and the diseased facial temperatures in the diseased facial temperature point set are respectively summarized according to the facial acupoints to obtain multiple diseased acupoint temperature sets, wherein the diseased acupoint temperature set includes multiple diseased acupoint temperatures, and the following operations are performed on each of the multiple diseased acupoint temperature sets: Obtaining an acupoint temperature mean based on the diseased acupoint temperature set, wherein the acupoint temperature mean is the mean of temperatures of multiple diseased acupoints in the diseased acupoint temperature set, and summarizing the acupoint temperature means to obtain an acupoint temperature mean set; Based on the update information set, an updated age mean is obtained, wherein the updated age mean is the mean of the patient age corresponding to each of the multiple historical information corresponding to the update information set; using the update information set, an updated weight change rate set is obtained, wherein the updated weight change rate set includes multiple updated weight change rates, and the updated weight change rates correspond to the historical information in the update information set one by one; based on the updated weight change rate set, an updated weight change mean is obtained, wherein the updated weight change mean is the mean of the multiple updated weight change rates in the updated weight change rate set; The user age of the smart scale is obtained, and a disease prediction matrix is ​​constructed based on the user age, acupoint temperature mean set, updated age mean, and updated weight change mean. The disease prediction matrix is ​​as follows: Among them, Q represents the disease prediction matrix, h0 represents the use age, v0 represents the target weight change rate, t1, t2, t n They represent the first target facial temperature, the second target facial temperature and the nth target facial temperature in the target facial temperature point set, respectively. h1 and v1 represent the updated age mean and updated weight change mean corresponding to the first updated information set in one or more updated information sets, respectively. t 11 ,t 12 ,t 1n They represent the first acupoint temperature mean, the second acupoint temperature mean and the nth acupoint temperature mean in the acupoint temperature mean set respectively, and u represents a total of u updated information sets; Calculating disease prediction values ​​using a disease prediction matrix and a pre-constructed disease prediction relationship, summarizing the disease prediction values ​​to obtain a disease prediction value set, and performing a sorting operation on the disease prediction values ​​in the disease prediction value set in ascending order to obtain an initial disease prediction sequence; Using a preset disease prediction threshold, a target disease sequence is identified in an initial disease prediction sequence, wherein the disease prediction values ​​in the target disease sequence are all less than or equal to the disease prediction threshold, and a predicted disease sequence is obtained based on the target disease sequence.

9. The disease prediction method for a smart scale according to claim 8, characterized in that: The disease prediction relationship is as follows: Among them, Y represents the disease prediction value, ω, They are all preset coefficients, j represents the element in the j-th row in the disease prediction matrix, and j is an integer greater than or equal to 2 and less than or equal to u.

10. A disease prediction system for a smart scale, characterized in that: The system comprises: A prediction environment confirmation module, used to receive a prediction instruction and confirm a prediction environment based on the prediction instruction, wherein the prediction environment includes a smart scale and a prediction system, wherein the prediction system includes a data acquisition unit, a data collection unit, a data analysis unit and a prediction feedback unit, wherein the smart scale includes a weight acquisition unit, a fingerprint acquisition unit, a facial acquisition unit and a facial temperature detection unit; A user information collection module, used to confirm receiving a data collection instruction from a data collection unit, and to obtain a first data set based on the data collection instruction, wherein the first data set includes a plurality of first data sets, and the first data set includes a reference facial image, a reference fingerprint image, and a reference weight time series, wherein the reference weight time series includes a plurality of reference weight groups, and the reference weight group consists of a reference weight and a measurement time; Confirming receipt of a data collection instruction from a data collection unit, starting the smart scale based on the data collection instruction, and using the started smart scale to obtain detection information, wherein the detection information includes a target facial image, a target fingerprint image, a target weight group, and a target facial temperature point set, and the target weight group includes a target weight and a weight collection time, and the target facial temperature point set includes a plurality of target facial temperatures, and based on the target fingerprint image corresponding to the detection information, confirming a second data group sequence in the first data group set, wherein the second data group sequence includes one or more second data groups; A reference information acquisition module, used to identify a target data group in the second data group sequence using the target facial image corresponding to the detection information, and to update a reference weight time series corresponding to the target data group using the target weight group corresponding to the detection information to obtain a target weight time series; Confirming receipt of a data analysis instruction from a data analysis unit, and using the data analysis instruction to obtain a historical information set, wherein the historical information set includes a plurality of patient information, wherein the patient information includes a disease name, a patient age, and a patient weight time series, wherein the patient weight time series includes a plurality of patient weight groups, and the patient weight group includes a patient weight and a patient measurement time; A user information analysis module, used to obtain one or more target information sets based on the historical information set; The target weight time series is used to identify a predicted disease sequence in one or more target information sets, and the predicted disease sequence is sent to an initiator of a prediction instruction based on the prediction feedback unit to achieve disease prediction.

Images